COMPUTER ENGINEERING, INFORMATION SYSTEMS AND TECHNOLOGIES

Method of Dynamic Optimal Distribution of the Applications Flow in Multi-Server Interactive Systems

Authors

V. O. Gnatyuk ORCID 0000-0002-4916-7149
State University «Kyiv Aviation Institute»
K. Yu. Zander ORCID 0009-0006-4944-9249
State University “Kyiv Aviation Institute”
DOI https://doi.org/10.31649/1997-9266-2026-186-3-6-16

Keywords

load balancing interactive system multiserver architecture optimal distribution method dynamic redistribution token bucket algorithm

Abstract

The paper presents a dynamic optimal method of request flows distribution in multi-server interactive systems aimed at achieving adaptive load balancing under conditions of non-stationary and unpredictable traffic. The proposed approach ensures real-time adjustment of the request flow among parallel servers based on the current load coefficients, thereby maintaining system stability and minimizing the probability of overloads. A structural-functional model of the proposed method is developed, consisting of modules for traffic smoothing, dynamic demultiplexing, and load equalization across the server line.

A modified version of the “token bucket” algorithm is introduced to convert a non-stationary and pulsating incoming flow into quasi-stationary traffic segments that can be processed by discrete control mechanisms. The model continuously measures instantaneous load parameters for each server and performs iterative redistribution of queued requests between overloaded and underloaded nodes. In case of critical congestion, additional servers can be automatically activated, while in periods of low intensity, redundant servers are temporarily deactivated to optimize resource utilization.

The proposed method can be applied to the design of real-time systems, cloud data centers, VoIP and IoT platforms, and 5G core networks, where maintaining stable performance under variable loads is a critical requirement. The approach enhances system scalability, reduces latency and request loss probability, and provides a foundation for implementing intelligent software-based controllers for adaptive load balancing. The proposed software implementation confirmed the efficiency of the developed method for dynamic optimal distribution of the requests flow in multi-server interactive systems. The algorithm provides adaptive load balancing, reduces the probability of overloads and loss of requests, and can also be integrated into real-time systems, SDN platforms, VoIP servers or data centers.

183 91

How to Cite

[1]
“Method of Dynamic Optimal Distribution of the Applications Flow in Multi-Server Interactive Systems”, Вісник ВПІ, no. 3, pp. 6–16, Jul. 2026, doi: 10.31649/1997-9266-2026-186-3-6-16.

Author Biographies

V. O. Gnatyuk, State University «Kyiv Aviation Institute»

Cand. Sc. (Eng.), Associate Professor, Head of the Chair of Telecommunications and Radioelectronic Systems

K. Yu. Zander, State University “Kyiv Aviation Institute”

Post-Graduate Student of the Chair of Telecommunications and Radioelectronic Systems

References

N. Olifer, V. Olifer, “Computer Networks: Principles,” Technologies and Protocols for Network Design, NJ: Wiley, 2005. 1008 с. [Electronic resource]. Available: https://link.springer.com/book/10.1007/978-3-031-17601-2 .
F. Miguelez, J. Doncel, and B. J. Prabhu, “Load-balancing for multi-skilled servers with Bernoulli routing,” Ann Oper Res, no. 312, pp. 949-971, 2022. https://doi.org/10.1007/s10479-022-04532-7 .
Kaur Shubhinder, and Kaur Gurpreet, “A Review of Load Balancing Strategies for Distributed Systems,” International Journal of Computer Applications, no. 121, pp. 45-47, 18, July 2015. https://doi.org/10.5120/21644-4985 .
J. Zhou, U. K. Lilhore, et al. “Comparative analysis of metaheuristic load balancing algorithms for efficient load balancing in cloud computing,” J Cloud Comp. no. 12, 85, 2023. https://doi.org/10.1186/s13677-023-00453-3 .
K. A. Vani, and K. N. RamaMohanBabu, “An Intelligent Server load balancing based on Multi-criteria decision-making in SDN”, IJECES, vol. 14, no. 4, pp. 433-442, Apr. 2023. [Electronic resource]. Available: https://ijeces.ferit.hr/index.php/ijeces/article/view/1946 .